MCP plugin for the AI-native spreadsheet

Connect your AI agent
to a spreadsheet it can’t break.

Layerz is an MCP server Claude, ChatGPT or any agent calls natively. Read model structure, update assumptions, compute projections, export Excel, without re-explaining context every session. Named references, so the formulas hold when the agent touches them.

MCP-compatible · BYOA · Export to standard .xlsx

The problem with AI + finance today

Claude is powerful — the layer underneath isn't.

You use Claude. You build financial analyses in chat. The next session, you start over.

There's no persistent model structure your agent can navigate. You paste numbers, re-explain assumptions, rebuild context.

What the MCP plugin gives your agent

A model your agent can actually navigate.

Your agent navigates the model. You review the outputs. The structure persists across sessions.

Read model structure

Variable names, types, formulas, dependencies.

Query computed values

Revenue, EBITDA, cash flow, any output at any period.

Update assumptions

Change a growth rate or headcount number, all outputs recompute automatically.

Export Excel

Trigger a clean .xlsx from your agent session.

BYOA — Bring your own agent

Your prompts, your data, your environment.

Layerz does not capture your Claude session. Connect your own Claude Max subscription or API key. Layerz is the structured backend, not the middleware.

Supported: Claude (MCP), ChatGPT and Codex (plugin), Claude Code, any MCP-compatible agent.

How to connect

Three steps to a connected agent.

Opens claude.ai with the Layerz connector pre-filled, or the Layerz plugin on chatgpt.com (ChatGPT and Codex). You confirm, sign in, done. Or set it up manually below.

1

Add the Layerz MCP server

One click from Claude or the ChatGPT plugin directory, or add the connector to your client by hand.

2

Authenticate

Sign in via OAuth or paste your Layerz API key.

3

Call layerz_* tools

Your agent now has access to layerz_read, layerz_patch, layerz_get_model and 27 more tools.

→ Full MCP reference and llms.txt

MCP clients

Install once in your agent of choice.

ClientAuthInstall
ClaudeOAuthSettings → Connectors → Add custom connector
Claude CoworkOAuthclaude.ai → Settings → Connectors → Add custom connector
Claude CodeOAuthclaude mcp add -t http layerz https://layerz.cc/mcp
ChatGPTOAuthchatgpt.com/plugins → Layerz → Connect
OpenAI CodexOAuthcodex mcp add layerz --url https://layerz.cc/mcp
GrokOAuthgrok.com/connectors → New connector → Custom
Grok BotOAuthIn the chat: "Add the remote MCP server https://layerz.cc/mcp", or Connect apps → custom
Mistral Le ChatOAuthSettings → Connectors → Add custom MCP connector
OpenCodeOAuthopencode.json: {"mcp":{"layerz":{"type":"remote","url":"https://layerz.cc/mcp","oauth":{}}}} then: opencode mcp auth layerz

Full install guide on GitHub

What you can build

From prompt to model to .xlsx.

Auto-populated budget models

Your agent fills a model structure from a prompt — assumptions first, then projections. Change one variable, all outputs update. No re-run.

Persistent unit economics

Define CAC, LTV, payback period once. Query across Claude sessions without rebuilding context.

Multi-scenario analysis

Run base / upside / downside on a shared model structure. Export any scenario to .xlsx — your colleagues get a clean file, they never see the agent.

How Layerz compares

Dated facts, and when the other tool is the right choice.

  • Layerz vs Claude

    Claude on its own can draft a financial model in a chat, keep instructions and files in a Project, and create an .xlsx file with its built-in skills. Layerz is not an alternative to Claude: it is a structured spreadsheet that Claude connects to through MCP, so the model keeps named variables, a history and its conventions between sessions. Use Claude alone for a one-off draft; add Layerz when the same model is updated every month, by you or by several people.

  • Layerz vs Claude in Excel

    Claude in Excel is Anthropic's add-in that reads and edits an open workbook, cites the cells it uses, and is included in paid Claude plans. Layerz is a structured spreadsheet that the same Claude drives through MCP: the model keeps named variables, a history and its conventions between sessions, and exports to Excel with live formulas. Use Claude in Excel to work on a workbook you received; use Layerz when the model has to survive the next edit, the next session and a reviewer, and many users do both.

  • Layerz vs ChatGPT for Excel

    ChatGPT for Excel is OpenAI's add-in that builds and updates models in the open workbook, cites the cells it uses and asks before editing; OpenAI made it generally available on all ChatGPT plans on 5 May 2026. Layerz is a structured spreadsheet that an AI agent drives through MCP, keeping named variables, a history and the model's conventions between sessions, with an Excel export on every plan. Use ChatGPT for Excel to work on a workbook in front of you; use Layerz when the same model is maintained month after month.

  • Layerz vs Copilot in Excel

    Copilot in Excel is Microsoft's AI inside Excel: with a Microsoft 365 Copilot licence it adds finance skills such as a DCF or a variance analysis, data connectors to providers like FactSet and S&P Global, and edits tracked in Show Changes. Layerz is a structured spreadsheet that your own Claude drives through MCP, keeping named variables, a history and the model's conventions between sessions, with a standard .xlsx export. Choose Copilot when the company standardises on Microsoft 365 and its data providers; choose Layerz for a model you maintain with Claude across sessions and clients.

  • Layerz vs Shortcut

    Shortcut is an AI agent for Excel that drafts DCF, LBO and three-statement models in the workbook, sold on credits (Pro at $100 per month billed annually, as of 2026-10-19). Layerz is a structured spreadsheet driven by your own Claude through MCP, free for one editor. Choose Shortcut for the fastest first draft inside Excel; choose Layerz to keep the model's logic, history and conventions across sessions, and note that a Shortcut-built workbook can be imported into Layerz.

  • Layerz vs Excel

    Layerz is a spreadsheet: a structured one, built so an AI agent can edit it without breaking it. Excel stays the universal format and the right tool for one-off analysis, offline work, VBA and Power Query. Layerz keeps the model logic in named variables with a history, and exports a standard .xlsx with live formulas on every plan, so the client never needs Layerz.

  • Layerz vs Pigment

    Pigment is a planning platform for company-wide budgeting and forecasting, with built-in AI agents, a Pigment MCP Server and no published price (as of 2026-10-19). Layerz is a structured spreadsheet for one model that one person builds, driven by their own Claude and exported to Excel, free for one editor. Choose Pigment to run planning across departments; choose Layerz for a model you build, version and hand over.

  • Layerz vs Anaplan

    Anaplan is an enterprise planning platform for connected planning across a large organisation, with built-in agents (CoModeler, Custom Analyst and Agent Studio, announced in March 2026) and no published price. Layerz is a self-serve structured spreadsheet driven by your own Claude, free for one editor. Choose Anaplan for connected planning across a large organisation; choose Layerz for a model a small team owns and exports to Excel.

All comparisons

Example prompts

Say it in plain English. Your agent does the modeling.

“Show me the revenue assumptions in my latest Layerz model and explain how they drive EBITDA.”

layerz_list_modelslayerz_read

“Raise the churn assumption to 2.5% from March and show me the impact on year-end cash.”

layerz_patchlayerz_read

“Create an upside scenario with 20% faster hiring, compare it to base, then export it to Excel.”

layerz_update_branchlayerz_patchlayerz_export

Questions, or stuck on setup? Write to [email protected].

Build the structure once. Query it from every session.

MCP-compatible · BYOA · Export to standard .xlsx

Layerz for AI Agents | MCP Financial Model Plugin for Claude and ChatGPT